{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4GSPI7AUMFIIJVICS42JE2PF6T","short_pith_number":"pith:4GSPI7AU","schema_version":"1.0","canonical_sha256":"e1a4f47c14615084d50297349269e5f4dea1fc2a407378d5ae9a8d56cce261cb","source":{"kind":"arxiv","id":"2411.06728","version":2},"attestation_state":"computed","paper":{"title":"On the Principles of ReLU Networks with One Hidden Layer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Changcun Huang","submitted_at":"2024-11-11T05:51:11Z","abstract_excerpt":"A neural network with one hidden layer or a two-layer network (regardless of the input layer) is the simplest feedforward neural network, whose mechanism may be the basis of more general network architectures. However, even to this type of simple architecture, it is also a ``black box''; that is, it remains unclear how to interpret the mechanism of its solutions obtained by the back-propagation algorithm and how to control the training process through a deterministic way. This paper systematically studies the first problem by constructing universal function-approximation solutions. It is shown"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.06728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T05:51:11Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"b686b834afd4e047581e82bc98dd2f340f9cee41514366c1e28a00ede848cc67","abstract_canon_sha256":"e9a731b91be4d63081f416be0323fd408cb3ff6c4e1b689edfafc163fd39f477"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:10.997450Z","signature_b64":"DoO/byC65O3XwLOz+Pjt8gmmTORT9vBmHduUrDIxCyZD1pUfBZsdMXvGZ9pljH63pOxcnElvT9LzNJjaXcOrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1a4f47c14615084d50297349269e5f4dea1fc2a407378d5ae9a8d56cce261cb","last_reissued_at":"2026-07-05T11:35:10.996938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:10.996938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Principles of ReLU Networks with One Hidden Layer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Changcun Huang","submitted_at":"2024-11-11T05:51:11Z","abstract_excerpt":"A neural network with one hidden layer or a two-layer network (regardless of the input layer) is the simplest feedforward neural network, whose mechanism may be the basis of more general network architectures. However, even to this type of simple architecture, it is also a ``black box''; that is, it remains unclear how to interpret the mechanism of its solutions obtained by the back-propagation algorithm and how to control the training process through a deterministic way. This paper systematically studies the first problem by constructing universal function-approximation solutions. It is shown"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06728","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.06728/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.06728","created_at":"2026-07-05T11:35:10.996995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06728v2","created_at":"2026-07-05T11:35:10.996995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06728","created_at":"2026-07-05T11:35:10.996995+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GSPI7AUMFII","created_at":"2026-07-05T11:35:10.996995+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GSPI7AUMFIIJVIC","created_at":"2026-07-05T11:35:10.996995+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GSPI7AU","created_at":"2026-07-05T11:35:10.996995+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07035","citing_title":"On the Principles of Deep Feedforward ReLU Networks","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4GSPI7AUMFIIJVICS42JE2PF6T","json":"https://pith.science/pith/4GSPI7AUMFIIJVICS42JE2PF6T.json","graph_json":"https://pith.science/api/pith-number/4GSPI7AUMFIIJVICS42JE2PF6T/graph.json","events_json":"https://pith.science/api/pith-number/4GSPI7AUMFIIJVICS42JE2PF6T/events.json","paper":"https://pith.science/paper/4GSPI7AU"},"agent_actions":{"view_html":"https://pith.science/pith/4GSPI7AUMFIIJVICS42JE2PF6T","download_json":"https://pith.science/pith/4GSPI7AUMFIIJVICS42JE2PF6T.json","view_paper":"https://pith.science/paper/4GSPI7AU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06728&json=true","fetch_graph":"https://pith.science/api/pith-number/4GSPI7AUMFIIJVICS42JE2PF6T/graph.json","fetch_events":"https://pith.science/api/pith-number/4GSPI7AUMFIIJVICS42JE2PF6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GSPI7AUMFIIJVICS42JE2PF6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GSPI7AUMFIIJVICS42JE2PF6T/action/storage_attestation","attest_author":"https://pith.science/pith/4GSPI7AUMFIIJVICS42JE2PF6T/action/author_attestation","sign_citation":"https://pith.science/pith/4GSPI7AUMFIIJVICS42JE2PF6T/action/citation_signature","submit_replication":"https://pith.science/pith/4GSPI7AUMFIIJVICS42JE2PF6T/action/replication_record"}},"created_at":"2026-07-05T11:35:10.996995+00:00","updated_at":"2026-07-05T11:35:10.996995+00:00"}